LightOnOCR 3 0.8B needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 30 quants, from 0.3 GB (Q1_0) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
LightOnOCR‑3‑0.8B – lightweight OCR with visual grounding
LightOnOCR‑3‑0.8B is a 0.8B‑parameter OCR model built on the Qwen3.5 vision‑language architecture. It supports transcription, grounding with bounding boxes, image descriptions, and chart data extraction. The model is released under Apache 2.0 for research and commercial use.
Good at
- Transcription of page text
- Grounding with bounding boxes and labels
- Visual description of images and charts
Limits
- No vision support beyond OCR
- Requires 8 k context for full memory estimate
- License is Apache 2.0
Best for
- OCR on documents with tables and forms
- Grounded text extraction for PDFs
- Rapid deployment in lightweight pipelines
Who it’s for. Developers needing a single model for OCR and visual understanding in document workflows. The model is suitable for research and commercial applications under an Apache 2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q1_0 | 0.3 GB | 1.2 GB | Fits | Get file → | |
| IQ1_S | 0.3 GB | 1.2 GB | Fits | Get file → | |
| IQ1_M | 0.3 GB | 1.2 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q2_0 | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ2_M | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XXS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q2_K_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ3_XS | 0.4 GB | 1.3 GB | Fits | Get file → | |
| IQ3_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ3_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_0 | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ4_NL | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_1 | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q5_0 | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_1 | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| BF16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 0.47 GB, memory 1.4 GB). If memory is tighter, IQ4_XS (0.5 GB, 1.4 GB) or IQ3_M (0.45 GB, 1.4 GB) are suitable. For maximum speed, Q6_K (0.63 GB, 1.5 GB) or Q8_0 (0.81 GB, 1.7 GB) can be used when ample VRAM is available.
What GPU do you need for LightOnOCR 3 0.8B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is BF16 (1.5 GB file, about 2.4 GB in use).
Which LightOnOCR 3 0.8B quant should you choose?
Q4_K_M is the usual starting point for LightOnOCR 3 0.8B: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q1_0 at 0.3 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LightOnOCR 3 0.8B
How much VRAM does LightOnOCR 3 0.8B need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run LightOnOCR 3 0.8B on an 8 GB GPU?
Yes, with BF16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LightOnOCR 3 0.8B GGUF?
It depends on the quant: Q1_0 is 0.3 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.4 GB, Q2_0 is 0.4 GB, IQ2_XS is 0.4 GB and 24 more.
What context length does LightOnOCR 3 0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download LightOnOCR 3 0.8B GGUF?
The files are on Hugging Face in the NANI-Nithin/LightOnOCR-3-0.8B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does LightOnOCR 3 0.8B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run LightOnOCR‑3‑0.8B on 8 GB VRAM?
Yes, a Q4_K_M quantization uses about 1.4 GB of VRAM at 8 k context, leaving headroom for the OS and KV cache.
What is the context length of this model?
The model was trained with 262144 tokens and supports up to that context length.
Is the model licensed for commercial use?
Yes, it is released under the Apache 2.0 license, allowing commercial deployment.